User Feedback: ChatGPT 5.2 Web Experience Declines with Poor Instruction Following and Formatting Issues

User feedback from the Linux.do community indicates that ChatGPT 5.2 web version has significant user experience issues. Users point out that this version has poor instruction-following capabilities, with disorganized response formatting, excessive use of large and small headings, making it difficult to highlight key points and quickly access important information. Despite this, users believe the model’s basic intelligence level hasn’t significantly decreased compared to previous versions, but these experience issues actually affect users’ perception of the model’s ‘intelligence’. This feedback provides valuable reference for users currently using or considering upgrading to version 5.2, and also reflects potential problems AI products may encounter in practical applications.